Journal of System Simulation
Abstract
Abstract: The traditional modulation recognition algorithms are based on the Gaussian white noise channel, which significantly degrade recognition performance in complex channel conditions. Aiming at this problem, a modulation recognition algorithm based on A-ALDA (Anti-alias Linear Discriminant Analysis) and SSDAE (Stacked Sparse Denoising Autoencoders) is proposed. In this algorithm, A-ALDA algorithm reconstructs signal cumulants feature into new features, which has better separability. The combination of original features and new features is input into SSDAE for classification, and SSADE has the ability to extract key information and resist noise. Simulation results show that recognition accuracy of the proposed algorithm is higher than that of the existing algorithms, and recognition accuracy is improved under the condition of limited signal length and phase and frequency offset interference.
Recommended Citation
Guo, Yecai and Zhang, Haoran
(2021)
"Modulation Recognition Algorithm Based on Improved LDA and Autoencoders,"
Journal of System Simulation: Vol. 33:
Iss.
2, Article 27.
DOI: 10.16182/j.issn1004731x.joss.19-0326
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol33/iss2/27
First Page
494
Revised Date
2019-09-11
DOI Link
https://doi.org/10.16182/j.issn1004731x.joss.19-0326
Last Page
500
CLC
TP391
Recommended Citation
Guo Yecai, Zhang Haoran. Modulation Recognition Algorithm Based on Improved LDA and Autoencoders[J]. Journal of System Simulation, 2021, 33(2): 494-500.
DOI
10.16182/j.issn1004731x.joss.19-0326
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons